flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Johannes (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (FLINK-2094) Implement Word2Vec
Date Wed, 27 May 2015 13:59:17 GMT

    [ https://issues.apache.org/jira/browse/FLINK-2094?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14561006#comment-14561006
] 

Johannes commented on FLINK-2094:
---------------------------------

Some information below, as I looked into this algorithm before.

There is a pretty performant implementation available for python 
https://radimrehurek.com/gensim/models/word2vec.html

Which has a better annotated source code, as the original source code is very hard to read.

Also along similar lines, there is an implementation within the nd4j framework in Java, which
might be interesting to look at.

http://deeplearning4j.org/word2vec.html

There is also a very good Tutorial by the author of word2vec that describes how neural networks
can be used 

http://www.coling-2014.org/COLING%202014%20Tutorial-fix%20-%20Tomas%20Mikolov.pdf

> Implement Word2Vec
> ------------------
>
>                 Key: FLINK-2094
>                 URL: https://issues.apache.org/jira/browse/FLINK-2094
>             Project: Flink
>          Issue Type: Improvement
>          Components: Machine Learning Library
>            Reporter: Nikolaas Steenbergen
>            Assignee: Nikolaas Steenbergen
>            Priority: Minor
>
> implement Word2Vec
> http://arxiv.org/pdf/1402.3722v1.pdf



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message